File size: 2,078 Bytes
0ca7ed3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
from dotenv import load_dotenv
from langchain.chains import RetrievalQA
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.vectorstores import Chroma
from langchain.llms import GPT4All, LlamaCpp
import os
load_dotenv()
embeddings_model_name = os.environ.get("EMBEDDINGS_MODEL_NAME")
persist_directory = os.environ.get('PERSIST_DIRECTORY')
model_type = os.environ.get('MODEL_TYPE')
model_path = os.environ.get('MODEL_PATH')
model_n_ctx = os.environ.get('MODEL_N_CTX')
from constants import CHROMA_SETTINGS
def main():
embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
retriever = db.as_retriever()
# Prepare the LLM
callbacks = [StreamingStdOutCallbackHandler()]
match model_type:
case "LlamaCpp":
llm = LlamaCpp(model_path=model_path, n_ctx=model_n_ctx, callbacks=callbacks, verbose=False)
case "GPT4All":
llm = GPT4All(model=model_path, n_ctx=model_n_ctx, backend='gptj', callbacks=callbacks, verbose=False)
case _default:
print(f"Model {model_type} not supported!")
exit;
qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
# Interactive questions and answers
while True:
query = input("\nEnter a query: ")
if query == "exit":
break
# Get the answer from the chain
res = qa(query)
answer, docs = res['result'], res['source_documents']
# Print the result
print("\n\n> Question:")
print(query)
print("\n> Answer:")
print(answer)
# Print the relevant sources used for the answer
for document in docs:
print("\n> " + document.metadata["source"] + ":")
print(document.page_content)
if __name__ == "__main__":
main()
|